Yup, although technically not replaced because I never used either of those products because I don't like sending my code to their black box. I have 2x24GB AMD gpu's, gotten from gamers on my local marketplace, one is connected with a 40cm riser cable. Running Qwen 27B and am very happy with its performance. Q8 with 135k context (arbitrary number, I could push it to 256). I like to use qwen 35B3A for mapping out entire code paths through our relatively complicated codebase/infra at work.
I think it's so good that I now scour the local marketplaces for good buys on 24GB cards that don't seem run through by miners and the likes, to build an even bigger rig for parallel execution.
Power usage is also totally not an issue, AI workload is very different from gaming.
tldr
llama.cpp-vulkan with opencode on total 48GB VRAM AMD cards on arch btw.
Judging by your profile location being in the netherlands, I think you are confusing the generic Ziggo ISP blocked page[1], where it lists Russia Today and Sputnik News and then in another post ThePirateBay
In this case, the ISP blocked it because the website is anna's archive [2], which was blocked around a year ago, but they have not made a post about that.
If you put "pcm." in front of the link it will work (for now)
You should probably edit your post, so as not to misinform. But I have to admit this confusion stems from bad decisions at the ISP.
When I just started out, I used to take everybody's on-call service because it paid well. Also had the advantage that I learned the ropes quicker. Now-a-days I'm very happy to not be awoken at 3am, even if 1 weekend incident would amount to a couple grand.
Anybody have a reliable, up-to-date pc build guide, for a full node? I find very fragmented information everywhere. I get that "most pc's can run Bitcoin core" but I'd like some more detailed information.
Do they want to keep a centralized database of everybody's eyeballs? I'm not sure I'm interested in this. I'm predicting people getting their eyes gauged out in high stakes robberies.
This is arguably the biggest thing to have happened to the VR space. I've been enjoying triple-A titles in VR, through UEVR since it came out a few months ago. It's reignited my love of gaming. The immersion is crucial to being able to forget about work and daily life for a couple hours.
I think it's so good that I now scour the local marketplaces for good buys on 24GB cards that don't seem run through by miners and the likes, to build an even bigger rig for parallel execution.
Power usage is also totally not an issue, AI workload is very different from gaming.
tldr llama.cpp-vulkan with opencode on total 48GB VRAM AMD cards on arch btw.